"""Deterministic fake embeddings for indexing/retrieval tests.

Identical text maps to an identical unit vector (cosine distance 0);
unrelated texts land near-orthogonal. Semantics are exercised by the evals
against the real endpoint — these tests cover the SQL plumbing.
"""

import hashlib
import math
import random

from app.models import EMBEDDING_DIM


def deterministic_embedding(text: str) -> list[float]:
    seed = hashlib.sha256(text.encode()).digest()
    rng = random.Random(seed)
    vector = [rng.uniform(-1.0, 1.0) for _ in range(EMBEDDING_DIM)]
    norm = math.sqrt(sum(value * value for value in vector))
    return [value / norm for value in vector]


async def fake_embed(texts: list[str], *, role: str = "embedding") -> list[list[float]]:
    return [deterministic_embedding(text) for text in texts]